A technique selects and serves local information items (e.g., news articles) to users. In a first stage, the technique uses a machine-trained localness-determining system to determine whether a candidate information item contains the kind of information that qualifies as locally-themed. In a second stage, a scope-determining system determines a particular geographic region associated with the information item. The technique then selectively serves the information item to a particular consumer upon determining that the particular consumer is located in the particular geographic region associated with the item. In some implementations, the scope-determining system describes the particular geographic region of the information item using a set of geohashes, and describes the location of the consumer using at least one geohash. The technique uses an ensemble approach to identify the particular geographic region of the item, and to generate training examples for use in training the localness-determining system.
Legal claims defining the scope of protection, as filed with the USPTO.
2. The computer-implemented method of claim 1, wherein the localness-determining system uses a transformer-based classifier model.
3. The computer-implemented method of claim 1, wherein the item-region information uses a set of geohashes to describe the item region, and wherein the consumer-region information uses at least one geohash to describe the consumer region, each geohash being created by a geohash encoding technique, the geohash encoding technique being a curve-filling technique that provides a way of encoding map blocks of prescribed size and location using respective alphanumeric codes.
8. The computer-implemented method of claim 7, wherein the prescribed test involves determining whether the particular region has a frequency-of-occurrence in the distribution that is lower than a maximum frequency-of-occurrence in the distribution, by a prescribed normalized amount.
10. The computer-implemented method of claim 1, wherein the method further comprises generating output information for presentation to the consumer that identifies the candidate information item and/or that identifies information extracted from the candidate information item.
11. The computer-implemented method of claim 1, wherein the localness-determining system is produced by a training system based on a set of training examples, wherein the training examples are produced by plural example-mining processes.
19. The computing system of claim 17, wherein the localness-determining system is produced by a training system based on a set of training examples, wherein the training examples are produced by plural example-mining processes.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
April 3, 2023
October 29, 2024
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.